Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add product-on-purpose/pm-skills --skill define-hypothesisgit clone --depth 1 https://github.com/product-on-purpose/pm-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/product-on-purpose/pm-skills/define-hypothesis)<a href="https://agentmods.dev/skills/product-on-purpose/pm-skills/define-hypothesis"><img src="https://agentmods.dev/badge/skills/product-on-purpose/pm-skills/define-hypothesis/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/product-on-purpose/pm-skills/define-hypothesis"><img src="https://agentmods.dev/badge/skills/product-on-purpose/pm-skills/define-hypothesis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00061 | $0.00812 |
| Opus 5 | $0.00030 | $0.00406 |
| Sonnet 5 | $0.00012 | $0.00162 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
define-hypothesis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- define-hypothesis — 98% identical, 12 lines differ
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hypothesis
A hypothesis is a testable prediction about how a change will affect user behavior or business outcomes. It transforms assumptions into explicit statements that can be validated or invalidated through experimentation. Well-formed hypotheses prevent teams from building features based on untested beliefs and create shared understanding of what success looks like.
When to Use
- After problem framing, before committing to a solution
- When designing experiments or A/B tests
- When team members have differing assumptions about user behavior
- Before investing significant engineering resources in a feature
- When pivoting direction and need to validate the new approach
When NOT to Use
- You are ready to design the actual A/B test (variants, sample size, duration) -> use
measure-experiment-design; this skill frames what to test, not how - The problem itself is still unframed -> use
define-problem-statementfirst - You want to organize many assumptions and ideas into a discovery structure -> use
define-opportunity-tree - The team needs the full business-model picture, not one testable claim -> use
foundation-lean-canvas
Instructions
When asked to create a hypothesis, follow these steps:
-
State the Belief Articulate what you believe will happen. Use the structured format: "We believe that [action/change] for [target user] will [expected outcome]." Be specific about the intervention - vague hypotheses can't be tested.
-
Identify the Target User Define who this hypothesis applies to. A hypothesis about "users" is too broad. Specify the segment: new users in their first week, power users with 10+ sessions, churned users returning, etc.
-
Define the Expected Outcome What behavior change or result do you expect? Frame it in terms of user actions (complete onboarding, make a purchase, return within 7 days) rather than internal metrics when possible.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 73 lines · 61 tokens per session scan A 532e6df9892e
define-hypothesis is a skill published in the GitHub repository product-on-purpose/pm-skills (663 stars, last pushed yesterday), licensed Apache-2.0. It adds 61 tokens to every session and 812 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
idea-validator
Use when the user asks to validate a product idea, stress-test an idea, evaluate whether an idea is good, or decide whether to build something. Do NOT use for prioritizing an existing backlog or reviewing a shipped feature — those need RICE scoring or a design review instead.
product-designer
Use when the user asks to review a design, critique a UI or mockup, give design feedback, or check a screen for usability and accessibility issues. Do NOT use for visual brand or aesthetic preference debates, or for reviewing copy before layout is settled.
prompt-engineer
Use when the user asks to improve, optimize, rewrite, debug, or shorten a prompt, or asks why a prompt is producing bad output. Do NOT use for writing a Claude Code SKILL.md — that needs skill structure rules, not prompt techniques.
status-update-writer
Use when the user asks to write a status update, weekly or monthly update, stakeholder update, project update, standup, status report, or QBR. Do NOT use for writing a PRD or a retro doc — those need different structures.
linkedin-post-writer
Use when the user asks to write, draft, or rewrite a LinkedIn post, turn notes or an article into a LinkedIn post, or fix a hook that is not landing. Do NOT use for X/Twitter threads, newsletters, or blog posts — those need different length and hook rules.
spec-from-conversation
Turn an unstructured stakeholder conversation, Slack thread, or meeting transcript into a structured spec (problem, goals, non-goals, success metrics, open questions). Use whenever a PM has raw conversational input and needs a first-draft spec, or when someone says "can you turn this into a doc" after a discussion.…